2015 Summer Internship Opportunity

We have one or two positions available for undergrad and graduate interns

Title: S
tudying the effect of tutor learning using SimStudent as a teachable agent 

Project Description:  
The primary purpose of the SimStudent project is to study cognitive and social theories of the effect of tutor learning, which is an empirically well-known phenomenon that students learn when they teach others.  To achieve this goal, we conduct classroom (in vivo) experiments to test specific hypotheses using two key technologies: APLUS and SimStudent.  APLUS is an online game-like learning environment in which students learn how to solve algebra equations by teaching a synthetic peer learner, called SimStudent. SimStudent is a machine-leaning agent that learns cognitive skills interactively when being tutored while solving problems.

SimStudent and APLUS provide a rich research environment.  For internship, there will be opportunities to study topics in computer science such like improving SimStudent’s learning mechanism, or issues in human-computer interaction such like improving interactions between (human) students and SimStudent.  For each individual summer intern projects, we will provide an independent research project based on the intern's interest and experience.  There are a number of potential projects that would be suitable for a summer intern projects including (but not limited to) the ones listed below:

(1) Educational Data-mining Study – How do students learn by teaching?  Using the study data mentioned above, a primary goal for this REU project would be to explore cognitive and social factors that mediate tutor learning. Knowledge and experience in advanced statistical analysis and/or data-mining techniques would be required. 

(2) Usability Study – What makes the Learning-by-Teaching environment more user-friendly, hence facilitating better tutor learning?  From a human-computer interaction (HCI) point of view, improvement of the system’s usability is an essential key for success in accomplishing our research agenda. In this project, the REU intern would apply various HCI methods to evaluate the system’s usability and explore key HCI factors to maximize tutor learning. Knowledge and experience in HCI methods would be required. 

(3) Prior Knowledge Study – How do the “individual” differences in SimStudent (i.e., the tutee) affect tutor learning?  By manipulating the initial background knowledge of SimStudent, we can control the speed and accuracy of SimStudent’s learning. For example, SimStudent may start with a certain amount of knowledge for equation solving, or SimStudent might have immature or even irrelevant background knowledge that slows down the learning rate and causes more errors. The goal of this REU project would be to study how such differences affect the student tutor’s learning.  Knowledge and skills of Java programming would be required. 

(4) Affective Agent Study – How does the appearance of SimStudent and its functionality affect tutor learning? What if SimStudent has emotions and expresses its affective status?  Can SimStudent share its affect with the student and if so how would such a sympathetic pedagogical-agent influence tutor learning? The goal of this REU project would be to study an affective interaction between SimStudent and human students and to understand how such emotional interaction affects student tutor learning. Knowledge and experience in design and/or Java programming would be required. 

(5) Tutoring Interaction Study – How can we improve the interaction between SimStudent and students? So far, SimStudent only learns from steps demonstrated by the student.  It would be more natural and (perhaps) more pedagogically appropriate if the student could give a hint with his/her own everyday language (e.g., “you can subtract the same number from both sides”). Such natural language input could be used as a heuristic to navigate the search for induction. The goal of this REU project is to study a rich tutoring dialogue by implementing and testing an augmented dialogue facility in the learning-by-teaching environment. Knowledge and experience in computer science, in particular natural language processing, would be required.

How to apply:  Send a CV to Noboru Matsuda as shown below.

Contact: Noboru Matsuda <Noboru.Matsuda@tamu.edu>

  Department of Teaching, Learning, and Culture
  Texas A&M University